Machine Vision for Autonomous Vehicles
The development of autonomous vehicles is a hot topic taken up not only by industry but increasingly
by research institutions. The topic is not new. Already in the 80th
big research projects such as the European EUREKA project
“Prometheus” (PROgraMme for a European Traffic of Highest Efficiency
and Unprecedented Safety, 1986–1994) were aimed at finding new
solutions for increased road safety. However, the key finding gained
almost 30 years ago was not so much an increase in autonomy as
improved driver assistance, in order to provide more support to the
driver in more complex situations. But new algorithms and
implementations of Artificial Intelligence, sophisticated sensors
and sensor fusion techniques are currently promising a significant
improvement in the reliability of autonomous vehicles. In that
context a lot of challenging problems are waiting on an answer. To
them belong especially questions directed to changing environmental
conditions during the autonomous drive such as rain, fog, snow, and
in general difficult visibility conditions. If vehicles are to drive
fully autonomously in the future, systems are required which scan
the environment with high precision, high spatial and temporal
resolution and guarantee the necessary reliability even in these
difficult situations.
Today, a wealth of different sensors are integrated and combined.
The sensor and data fusion can be described as inadequate in current
configurations, since the individual data streams are processed and
interpreted in parallel. A combination of the results takes place
very late in the process chain. Inadequate results characterized by
latency and blurring are the result. The special session is
dedicated to that challenge. Various lectures address new approaches
for better dealing with such complex situations. To them belong new
ways of machine Learning for infrastructure monitoring, new LiDAR
sensors for obstacle recognition, and two new sensors for the
improvement of object recognition through scattering media.
Chairman: Prof. Wolfgang Osten
About Prof. Wolfgang Osten: he received the MSc/Diploma in Physics from the Friedrich-Schiller-University Jena in 1979. From 1979 to 1984 he was a member of the Institute of Mechanics in Berlin working in the field of experimental stress analysis and optical metrology. In 1983 he received the PhD degree from the Martin-Luther-University Halle-Wittenberg for his thesis in the field of holographic interferometry. From 1984 to 1991 he was employed at the Central Institute of Cybernetics and Information Processes ZKI in Berlin making investigations in digital image processing and computer vision. Between 1988 and 1991 he was heading the Institute for Digital Image Processing at the ZKI. In 1991 he joined the Bremen Institute of Applied Beam Technology (BIAS) to establish and to direct the Department Optical 3D-Metrology till 2002. Since September 2002 he has been a full professor at the University of Stuttgart and director of the Institute for Applied Optics. From 2006 till 2010 he was the vice rector for research and technology transfer of the Stuttgart University where he is currently the vice chair of the university council. His research work is focused on new concepts for industrial inspection and metrology by combining modern principles of optical metrology, sensor technology and image processing. Special attention is directed to the development of resolution enhanced technologies for the investigation of micro and nano structures.
Important Dates